[swg] RE: [openib-general] RE: [dat-discussions] socket based connectionmodel for IB proposal - round 3

Caitlin Bestler caitlinb at broadcom.com
Fri Nov 11 11:12:15 PST 2005


 


________________________________

	From: Renato Recio [mailto:recio at us.ibm.com] 
	Sent: Friday, November 11, 2005 11:01 AM
	To: Caitlin Bestler
	Cc: Kanevsky, Arkady; dat-discussions at yahoogroups.com; Sean
Hefty; openib-general at openib.org; swg at infinibandta.org
	Subject: Re: [swg] RE: [openib-general] RE: [dat-discussions]
socket based connectionmodel for IB proposal - round 3
	
	

	The CM cannot get a message from a non-priviliged requestor,
because a non-privilited requestor cannot insert the priviliged Q_Key
into the packet.
	
	
	

	 

But a non-privileged remote consumer could make a request of an existing
CM.
That existing CM would consider the entire "private data" field to be,
well, private.
It would obviously not validate any of it.
 
So getting the Q_Key does not guarantee that the private data is
validated.
There has to be a field outside of the private data that can only be set
by
privileged codes that means "I am aware of the expectation that I have
validated the standardized portion of the private data in this optional
format."
 
And yes, the Q-Key is how we know that assertion is coming from
privileged
remote software.
 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20051111/c2d82c46/attachment.html>


More information about the general mailing list